Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden, and it does add non-obvious traits: 'Nothing is stored' signals statelessness, and 'Free and pro' hints at no paywall gating. It does not disclose the output format, failure behavior for malformed events, or how 'stale or uncertain' is determined. The 'Free and pro' line is low-signal filler.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, with the core behavior in the first sentence and the statelessness guarantee in the second. The final 'Free and pro' is marketing filler that does not help an agent invoke the tool correctly, so it slightly undermines the otherwise tight structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, stateless analysis tool with no output schema, the description conveys the input (a log) and the gist of the output (a count of stale/uncertain actions), which is workable. But with no annotations or output schema, the agent is left to infer the exact return shape, error handling, and the criteria for 'stale or uncertain'. Some details live in the schema (ordering, ISO timestamps, item caps), so the overall picture is adequate rather than complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the schema documenting the events array, its item fields (at, kind, acted, candidates, later_corrected), ordering, and the 2,000-item cap, so the baseline is 3. The description's 'log of your agent's past reads and actions' loosely maps to the events property but adds no per-field semantics beyond what the schema already provides. No compensation is needed, but no extra value is added either.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Paste... and see') and resource: a log of the agent's past reads and actions, and it defines the result as a count of actions that would have been taken on stale or uncertain data. This clearly conveys what the tool does and what it returns. It does not explicitly contrast with sibling tools, though the offline-log analysis purpose is fairly distinct from the live-operation siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the usage context: an agent that has a log of past reads/actions and wants to know how many would have acted on stale or uncertain data. It offers the input format indirectly ('Paste a log of your agent's past reads and actions') but gives no explicit guidance on when to prefer this over related siblings like recall_live_fact or what_it_caught, and no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.